LEDGER introduces claim-to-evidence trace graphs to make LLM agent outputs auditable, addressing the challenge of verifying correctness in autonomous workflows that execute code, edit files, and ge...
Researchers audit three self-evolving financial AI agents (SkillOpt, AWM, ReasoningBank) in e-banking scenarios, finding that performance gains don't guarantee security preservation or behavioral c...
Research prototype binds AI policy decisions to cryptographically signed, durable audit records with explicit trust boundaries—critical infrastructure for AI systems in regulated accounting/audit e...
Researchers introduce LAVA, a modular AI framework for validating financial documents at scale in payroll, tax, and lending—handling heterogeneous layouts and enforcing business rules where current...
Fiducia-bench, a new research benchmark, shows that decomposing financial agents into components undermines governance—reducing escalation, abstention, and auditability compliance critical for regu...
Research on ProcessBench traces reveals LLMs soften audit verification thresholds by 2.8–11.5 percentage points when prior repair episodes are in context, reducing false alarms across 15 model vari...
AgentRelBench, a new reliability framework, tested nine LLM models on accounting operations and found systematic failures in irreversible tasks—exposing that single-run audits miss critical agent d...
Researchers propose Mandato, a protocol-level governance framework enforcing digitally signed mandates on AI agent actions with cryptographically chained audit trails—addressing authorization and a...
Research proposes Matrix, a causal-state layer for agentic workflows that enforces governed execution with inspectable provenance—critical for institutional settings like accounting where correct o...
Researchers propose 'Rule of Thumb' explainability framework to interpret AI decisions using partial information, with applications to LLM classification and AI system audits—relevant for accountan...
Researchers argue AI model evaluation for accounting must measure verification effort, not just correctness—identifying a new failure mode where auditors miss errors within budget constraints.
IntelliAudit uses retrieval-grounded multi-agent LLMs to automate IT audit evidence evaluation by synthesizing heterogeneous organizational data across policies and records—addressing the semantic ...
AppZen publishes playbook for new CFOs using AI-powered expense audit to establish credibility and improve forecasting accuracy in their first 100 days.
Research framework for auditing AI recommendation systems by comparing outputs against complete data census, addressing critical accountability gaps in AI-driven decision-making for high-stakes dom...
DataSnipper argues specialized audit AI agents deliver better results than generic LLMs for accounting tasks, highlighting domain-specific optimization over broad AI models.
CPA Practice Advisor publishes practical guidance on control frameworks accounting firms should implement before automating client closes with AI agents.
Fieldguide rolls out Field Financials and MCP tools to automate audit engagement stages, positioning toward an 'agentic firm' model where AI amplifies practitioner expertise.
Ernst & Young scales AI adoption across global audit practice, transforming auditors into AI developers to enhance thoroughness and client service.
Fieldguide releases Field Financials and Fieldguide MCP to automate audit workflows including financial statement drafting, peer reviews, and disclosure management, with new integrations for third-...
YC-backed SecondState automates financial data prep for audits and diligence using AI agents to build data pipelines with human approval gates, targeting the pre-analytics layer competitors skip.